2027 Event Agenda

As utilities race to deploy advanced analytics and AI, they inevitably hit a fundamental wall: legacy data is rarely mature enough to power true asset intelligence. Building a trustworthy Asset Health Index or running predictive risk algorithms requires high-fidelity data, but attempting an enterprise-wide, unfocused, expensive data cleanup often results in sunk costs without capturing value.

To break through this challenge, Dominion Energy Virginia undertook a comprehensive data assessment with their partner TRC. This initiative leveraged deep subject matter expertise to define what matters most for asset intelligence, layering those insights with the specific input requirements of advanced analytics vendors in the asset performance management space. The resulting strategy rejected the traditional clean everything mentality. Instead, it isolated the exact information supply chain required to feed incoming asset intelligence algorithms, focusing remediation strictly on data fields that directly drive risk and health weights.

One example of this targeted approach focused on missing or placeholder installation dates for distribution poles, a critical data element affecting degradation curves, asset health indices, risk models and AI-driven asset intelligence. Dominion is deploying tactical methodologies to infer pole ages (and many other data sets) and prime the data foundation.

This session moves past the standard AI hype to deliver a repeatable blueprint for technology readiness, helping utilities accelerate analytics initiatives while reducing implementation risk and focusing resources on the data that matters most. Attendees will learn the strategic value of shifting from broad data cleanup to targeted surgical readiness and how to apply this repeatable framework to ensure utility AI and advanced analytics deliver maximum value on day one.